GNN Tensor Flow Dashboard

Visualizing Data Transformations Through the Pipeline

Pipeline Overview

This dashboard visualizes how data transforms as it flows through the GNN pipeline:

Raw Time Series Data → Find Continuous Segments → Create Windows → Compute Adjacency Weights → Batch Data → Model Forward Pass

Raw Input Time Series

Starting point: time series data with missing values (shown as gaps).

Continuous Segments

Identifying continuous segments in the time series data without significant gaps.

Windowed Data

Creating fixed-size windows from continuous segments, standardizing values, and tracking missing data with masks.

Weighted Adjacency Matrix

Converting distance matrix to weighted adjacency matrix using Gaussian kernel.

Batched Data

Organizing data into batches for model training with shape transformations.

Model Architecture

Visualizing the STGNN model architecture that processes the tensor data.

Tensor Shape Transformations

Summary of how tensor shapes change through the pipeline:

Raw Time Series: Series[time] → shape: (n_timestamps,)
Windowed Data: X_by_sensor[node_id] → shape: (n_windows, window_size)
Batched Data: x → shape: (batch_size, num_nodes, seq_len, features)
Model Output: predictions → shape: (batch_size, num_nodes, horizon, features)
Raw Adjacency Matrix → shape: (num_nodes, num_nodes)
Weighted Adjacency Matrix → shape: (num_nodes, num_nodes)